Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1105 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0004

Data Index: 831802 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1009536 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0208. Min Act: -0.0004

Data Index: 735455 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0204. Min Act: -0.0004

Data Index: 748181 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1391254 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1459133 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1541202 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0188. Min Act: -0.0003

Data Index: 41287 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1037967 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1171180 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1477811 (Python Code)

Max Activating Token Index: 322

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1198746 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1653350 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1330250 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1024907 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1383165 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1587390 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0179. Min Act: -0.0003

Data Index: 355330 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0179. Min Act: -0.0003

Data Index: 159838 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1561928 (Python Code)

Max Activating Token Index: 24